Your diffusion model secretly knows the dimension of the data manifold

• URL: http://arxiv.org/abs/2212.12611v5
• Date: Thu, 25 May 2023 14:03:25 GMT
• Title: Your diffusion model secretly knows the dimension of the data manifold
• Authors: Jan Stanczuk, Georgios Batzolis, Teo Deveney, Carola-Bibiane Sch\"onlieb
• Abstract summary: A diffusion model approximates the gradient of the log density of a noise-corrupted version of the target distribution for varying levels of corruption. We prove that, if the data concentrates around a manifold embedded in the high-dimensional ambient space, then as the level of corruption decreases, the score function points towards the manifold.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this work, we propose a novel framework for estimating the dimension of the data manifold using a trained diffusion model. A diffusion model approximates the score function i.e. the gradient of the log density of a noise-corrupted version of the target distribution for varying levels of corruption. We prove that, if the data concentrates around a manifold embedded in the high-dimensional ambient space, then as the level of corruption decreases, the score function points towards the manifold, as this direction becomes the direction of maximal likelihood increase. Therefore, for small levels of corruption, the diffusion model provides us with access to an approximation of the normal bundle of the data manifold. This allows us to estimate the dimension of the tangent space, thus, the intrinsic dimension of the data manifold. To the best of our knowledge, our method is the first estimator of the data manifold dimension based on diffusion models and it outperforms well established statistical estimators in controlled experiments on both Euclidean and image data.

Related papers

• Convergence of Diffusion Models Under the Manifold Hypothesis in High-Dimensions [6.9408143976091745]
  Denoising Diffusion Probabilistic Models (DDPM) are powerful state-of-the-art methods used to generate synthetic data from high-dimensional data distributions. We study DDPMs under the manifold hypothesis and prove that they achieve rates independent of the ambient dimension in terms of learning the score. In terms of sampling, we obtain rates independent of the ambient dimension w.r.t. the Kullback-Leibler divergence, and $O(sqrtD)$ w.r.t. the Wasserstein distance.
  arXiv  Detail & Related papers  (2024-09-27T14:57:18Z)
• Learning on manifolds without manifold learning [0.0]
  Function approximation based on data drawn randomly from an unknown distribution is an important problem in machine learning. In this paper, we project the unknown manifold as a submanifold ambient hypersphere and study the question of constructing a one-shot approximation using specially designed kernels on the hypersphere.
  arXiv  Detail & Related papers  (2024-02-20T03:27:53Z)
• Scaling Riemannian Diffusion Models [68.52820280448991]
  We show that our method enables us to scale to high dimensional tasks on nontrivial manifold. We model QCD densities on $SU(n)$ lattices and contrastively learned embeddings on high dimensional hyperspheres.
  arXiv  Detail & Related papers  (2023-10-30T21:27:53Z)
• Generative Modeling on Manifolds Through Mixture of Riemannian Diffusion Processes [57.396578974401734]
  We introduce a principled framework for building a generative diffusion process on general manifold. Instead of following the denoising approach of previous diffusion models, we construct a diffusion process using a mixture of bridge processes. We develop a geometric understanding of the mixture process, deriving the drift as a weighted mean of tangent directions to the data points.
  arXiv  Detail & Related papers  (2023-10-11T06:04:40Z)
• Diffusion Models are Minimax Optimal Distribution Estimators [49.47503258639454]
  We provide the first rigorous analysis on approximation and generalization abilities of diffusion modeling. We show that when the true density function belongs to the Besov space and the empirical score matching loss is properly minimized, the generated data distribution achieves the nearly minimax optimal estimation rates.
  arXiv  Detail & Related papers  (2023-03-03T11:31:55Z)
• Score Approximation, Estimation and Distribution Recovery of Diffusion Models on Low-Dimensional Data [68.62134204367668]
  This paper studies score approximation, estimation, and distribution recovery of diffusion models, when data are supported on an unknown low-dimensional linear subspace. We show that with a properly chosen neural network architecture, the score function can be both accurately approximated and efficiently estimated. The generated distribution based on the estimated score function captures the data geometric structures and converges to a close vicinity of the data distribution.
  arXiv  Detail & Related papers  (2023-02-14T17:02:35Z)
• ManiFlow: Implicitly Representing Manifolds with Normalizing Flows [145.9820993054072]
  Normalizing Flows (NFs) are flexible explicit generative models that have been shown to accurately model complex real-world data distributions. We propose an optimization objective that recovers the most likely point on the manifold given a sample from the perturbed distribution. Finally, we focus on 3D point clouds for which we utilize the explicit nature of NFs, i.e. surface normals extracted from the gradient of the log-likelihood and the log-likelihood itself.
  arXiv  Detail & Related papers  (2022-08-18T16:07:59Z)
• Joint Manifold Learning and Density Estimation Using Normalizing Flows [4.939777212813711]
  We introduce two approaches, namely per-pixel penalized log-likelihood and hierarchical training, to answer the question. We propose a single-step method for joint manifold learning and density estimation by disentangling the transformed space. Results validate the superiority of the proposed methods in simultaneous manifold learning and density estimation.
  arXiv  Detail & Related papers  (2022-06-07T13:35:14Z)
• Hard-label Manifolds: Unexpected Advantages of Query Efficiency for Finding On-manifold Adversarial Examples [67.23103682776049]
  Recent zeroth order hard-label attacks on image classification models have shown comparable performance to their first-order, gradient-level alternatives. It was recently shown in the gradient-level setting that regular adversarial examples leave the data manifold, while their on-manifold counterparts are in fact generalization errors. We propose an information-theoretic argument based on a noisy manifold distance oracle, which leaks manifold information through the adversary's gradient estimate.
  arXiv  Detail & Related papers  (2021-03-04T20:53:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.